Job_Market_Research_2

Reading the Data Sets

#devtools::install_github("UrbanInstitute/urbnmapr")
library(readr)
library(patchwork)

## Warning: package 'patchwork' was built under R version 4.4.3

library(tidyverse)

## Warning: package 'tidyverse' was built under R version 4.4.2

## Warning: package 'ggplot2' was built under R version 4.4.2

## Warning: package 'tidyr' was built under R version 4.4.2

## Warning: package 'purrr' was built under R version 4.4.2

## Warning: package 'dplyr' was built under R version 4.4.2

## Warning: package 'forcats' was built under R version 4.4.2

## Warning: package 'lubridate' was built under R version 4.4.2

## ── Attaching core tidyverse packages ──────────────────────── tidyverse 2.0.0 ──
## ✔ dplyr     1.1.4     ✔ purrr     1.0.2
## ✔ forcats   1.0.0     ✔ stringr   1.5.1
## ✔ ggplot2   3.5.1     ✔ tibble    3.2.1
## ✔ lubridate 1.9.4     ✔ tidyr     1.3.1
## ── Conflicts ────────────────────────────────────────── tidyverse_conflicts() ──
## ✖ dplyr::filter() masks stats::filter()
## ✖ dplyr::lag()    masks stats::lag()
## ℹ Use the conflicted package (<http://conflicted.r-lib.org/>) to force all conflicts to become errors

library(urbnmapr)
library(sf)

## Warning: package 'sf' was built under R version 4.4.3

## Linking to GEOS 3.13.0, GDAL 3.10.1, PROJ 9.5.1; sf_use_s2() is TRUE

library(ggthemes)

## Warning: package 'ggthemes' was built under R version 4.4.2

library(scales)

## Warning: package 'scales' was built under R version 4.4.2

## 
## Attaching package: 'scales'
## 
## The following object is masked from 'package:purrr':
## 
##     discard
## 
## The following object is masked from 'package:readr':
## 
##     col_factor

library(readxl)
ind_posting <- read_csv("Indeed_Postings.csv")

## Rows: 1827 Columns: 2
## ── Column specification ────────────────────────────────────────────────────────
## Delimiter: ","
## dbl  (1): IHLIDXUS
## date (1): observation_date
## 
## ℹ Use `spec()` to retrieve the full column specification for this data.
## ℹ Specify the column types or set `show_col_types = FALSE` to quiet this message.

us_unemp <- read_csv("UNRATE.csv")

## Rows: 927 Columns: 2
## ── Column specification ────────────────────────────────────────────────────────
## Delimiter: ","
## dbl  (1): UNRATE
## date (1): observation_date
## 
## ℹ Use `spec()` to retrieve the full column specification for this data.
## ℹ Specify the column types or set `show_col_types = FALSE` to quiet this message.

counties_sf <- get_urbn_map(map = "counties", sf = TRUE)
states_sf <- get_urbn_map(map = "states", sf = TRUE)
labor_demand_size <- read_excel("LSE_2024_Anatomy_Labor_DemandPre-PostCOVID-Topa.xlsx", sheet = "Chart 1", skip = 5)

## New names:
## • `` -> `...1`

labor_demand_job <- read_excel("LSE_2024_Anatomy_Labor_DemandPre-PostCOVID-Topa.xlsx", sheet = "Charts 2", skip = 5)
labor_demand_size_job <- read_excel("LSE_2024_Anatomy_Labor_DemandPre-PostCOVID-Topa.xlsx", sheet = "Chart 3", skip = 5)

AL <- read_excel("UnemploymentReport.xlsx", skip = 2)

## New names:
## • `` -> `...13`

AK <- read_excel("UnemploymentReport (1).xlsx", skip = 2)

## New names:
## • `` -> `...13`

AZ <- read_excel("UnemploymentReport (2).xlsx", skip = 2)

## New names:
## • `` -> `...13`

AR <- read_excel("UnemploymentReport (3).xlsx", skip = 2)

## New names:
## • `` -> `...13`

CA <- read_excel("UnemploymentReport (4).xlsx", skip = 2)

## New names:
## • `` -> `...13`

CO <- read_excel("UnemploymentReport (5).xlsx", skip = 2)

## New names:
## • `` -> `...13`

CT <- read_excel("UnemploymentReport (6).xlsx", skip = 2)

## New names:
## • `` -> `...1`
## • `` -> `...14`

DE <- read_excel("UnemploymentReport (7).xlsx", skip = 2)

## New names:
## • `` -> `...1`
## • `` -> `...14`

DC <- read_excel("UnemploymentReport (8).xlsx", skip = 2)

## New names:
## • `` -> `...1`
## • `` -> `...14`

FL <- read_excel("UnemploymentReport (10).xlsx", skip = 2)

## New names:
## • `` -> `...1`
## • `` -> `...14`

GA <- read_excel("UnemploymentReport (11).xlsx", skip = 2)

## New names:
## • `` -> `...1`
## • `` -> `...14`

HI <- read_excel("UnemploymentReport (12).xlsx", skip = 2)

## New names:
## • `` -> `...1`
## • `` -> `...14`

ID <- read_excel("UnemploymentReport (13).xlsx", skip = 2)

## New names:
## • `` -> `...1`
## • `` -> `...14`

IL <- read_excel("UnemploymentReport (14).xlsx", skip = 2)

## New names:
## • `` -> `...1`
## • `` -> `...14`

IN <- read_excel("UnemploymentReport (15).xlsx", skip = 2)

## New names:
## • `` -> `...1`
## • `` -> `...14`

IA <- read_excel("UnemploymentReport (16).xlsx", skip = 2)

## New names:
## • `` -> `...1`
## • `` -> `...14`

KS <- read_excel("UnemploymentReport (17).xlsx", skip = 2)

## New names:
## • `` -> `...1`
## • `` -> `...14`

KY <- read_excel("UnemploymentReport (18).xlsx", skip = 2)

## New names:
## • `` -> `...1`
## • `` -> `...14`

LA <- read_excel("UnemploymentReport (19).xlsx", skip = 2)

## New names:
## • `` -> `...1`
## • `` -> `...14`

ME <- read_excel("UnemploymentReport (20).xlsx", skip = 2)

## New names:
## • `` -> `...1`
## • `` -> `...14`

MD <- read_excel("UnemploymentReport (21).xlsx", skip = 2)

## New names:
## • `` -> `...1`
## • `` -> `...14`

MA <- read_excel("UnemploymentReport (22).xlsx", skip = 2)

## New names:
## • `` -> `...1`
## • `` -> `...14`

MI <- read_excel("UnemploymentReport (23).xlsx", skip = 2)

## New names:
## • `` -> `...1`
## • `` -> `...14`

MN <- read_excel("UnemploymentReport (24).xlsx", skip = 2)

## New names:
## • `` -> `...1`
## • `` -> `...14`

MS <- read_excel("UnemploymentReport (25).xlsx", skip = 2)

## New names:
## • `` -> `...1`
## • `` -> `...14`

MO <- read_excel("UnemploymentReport (26).xlsx", skip = 2)

## New names:
## • `` -> `...1`
## • `` -> `...14`

MT <- read_excel("UnemploymentReport (27).xlsx", skip = 2)

## New names:
## • `` -> `...1`
## • `` -> `...14`

NE <- read_excel("UnemploymentReport (28).xlsx", skip = 2)

## New names:
## • `` -> `...1`
## • `` -> `...14`

NV <- read_excel("UnemploymentReport (29).xlsx", skip = 2)

## New names:
## • `` -> `...1`
## • `` -> `...14`

NH <- read_excel("UnemploymentReport (30).xlsx", skip = 2)

## New names:
## • `` -> `...1`
## • `` -> `...14`

NJ <- read_excel("UnemploymentReport (31).xlsx", skip = 2)

## New names:
## • `` -> `...1`
## • `` -> `...14`

NM <- read_excel("UnemploymentReport (32).xlsx", skip = 2)

## New names:
## • `` -> `...1`
## • `` -> `...14`

NY <- read_excel("UnemploymentReport (33).xlsx", skip = 2)

## New names:
## • `` -> `...1`
## • `` -> `...14`

NC <- read_excel("UnemploymentReport (34).xlsx", skip = 2)

## New names:
## • `` -> `...1`
## • `` -> `...14`

ND <- read_excel("UnemploymentReport (35).xlsx", skip = 2)

## New names:
## • `` -> `...1`
## • `` -> `...14`

OH <- read_excel("UnemploymentReport (36).xlsx", skip = 2)

## New names:
## • `` -> `...1`
## • `` -> `...14`

OK <- read_excel("UnemploymentReport (37).xlsx", skip = 2)

## New names:
## • `` -> `...1`
## • `` -> `...14`

OR <- read_excel("UnemploymentReport (38).xlsx", skip = 2)

## New names:
## • `` -> `...1`
## • `` -> `...14`

PA <- read_excel("UnemploymentReport (39).xlsx", skip = 2)

## New names:
## • `` -> `...1`
## • `` -> `...14`

RI <- read_excel("UnemploymentReport (41).xlsx", skip = 2)

## New names:
## • `` -> `...1`
## • `` -> `...14`

SC <- read_excel("UnemploymentReport (42).xlsx", skip = 2)

## New names:
## • `` -> `...1`
## • `` -> `...14`

SD <- read_excel("UnemploymentReport (43).xlsx", skip = 2)

## New names:
## • `` -> `...1`
## • `` -> `...14`

TN <- read_excel("UnemploymentReport (44).xlsx", skip = 2)

## New names:
## • `` -> `...1`
## • `` -> `...14`

TX <- read_excel("UnemploymentReport (45).xlsx", skip = 2)

## New names:
## • `` -> `...1`
## • `` -> `...14`

UT <- read_excel("UnemploymentReport (46).xlsx", skip = 2)

## New names:
## • `` -> `...1`
## • `` -> `...14`

VT <- read_excel("UnemploymentReport (47).xlsx", skip = 2)

## New names:
## • `` -> `...1`
## • `` -> `...14`

VA <- read_excel("UnemploymentReport (48).xlsx", skip = 2)

## New names:
## • `` -> `...1`
## • `` -> `...14`

WA <- read_excel("UnemploymentReport (49).xlsx", skip = 2)

## New names:
## • `` -> `...1`
## • `` -> `...14`

WV <- read_excel("UnemploymentReport (50).xlsx", skip = 2)

## New names:
## • `` -> `...1`
## • `` -> `...14`

WI <- read_excel("UnemploymentReport (51).xlsx", skip = 2)

## New names:
## • `` -> `...1`
## • `` -> `...14`

WY <- read_excel("UnemploymentReport (52).xlsx", skip = 2)

## New names:
## • `` -> `...1`
## • `` -> `...14`

state_names_1 <- c(
  "CT", "DE", "DC", "FL", "GA", "HI", "ID", "IL", "IN", "IA",
  "KS", "KY", "LA", "ME", "MD", "MA", "MI", "MN", "MS", "MO",
  "MT", "NE", "NV", "NH", "NJ", "NM", "NY", "NC", "ND", "OH",
  "OK", "OR", "PA", "RI", "SC", "SD", "TN", "TX", "UT", "VT",
  "VA", "WA", "WV", "WI", "WY"
)


for (state in state_names_1) {
  assign(state, get(state)[, -1])
}

state_names_2 <- c(
  "AL", "AK", "AZ", "AR", "CA", "CO", "CT", "DE", "DC", "FL", "GA", "HI", "ID", "IL",
  "IN", "IA", "KS", "KY", "LA", "ME", "MD", "MA", "MI", "MN", "MS", "MO", "MT", "NE",
  "NV", "NH", "NJ", "NM", "NY", "NC", "ND", "OH", "OK", "OR", "PA", "RI", "SC", "SD",
  "TN", "TX", "UT", "VT", "VA", "WA", "WV", "WI", "WY"
)

for (state in state_names_2) {
  assign(state, get(state)[, -13])
}

unemp_county <- rbind(AL, AK,  AZ, AR,   CA,  CO,  CT,  DE,  DC,  FL,  GA,  HI,  ID,  IL,  IN,  IA,  KS,  KY,  LA,  ME,  MD,  MA, MI, MN,  MS,  MO,  MT,  NE,  NV,  NH,  NJ,  NM,  NY,  NC,  ND,  OH,  OK,  OR,  PA,  RI,  SC,  SD,  TN,  TX, UT, VT,  VA,  WA,  WV,  WI, WY )

str(unemp_county)

## tibble [3,296 × 13] (S3: tbl_df/tbl/data.frame)
##  $ FIPS                          : chr [1:3296] "01000" "01001" "01003" "01005" ...
##  $ Name                          : chr [1:3296] "Alabama" "Autauga County, AL" "Baldwin County, AL" "Barbour County, AL" ...
##  $ 2015                          : num [1:3296] 6.1 5.2 5.6 8.9 6.7 5.4 8 7.6 7.1 6.1 ...
##  $ 2016                          : num [1:3296] 5.9 5.1 5.4 8.4 6.5 5.4 6.9 6.9 6.6 5.5 ...
##  $ 2017                          : num [1:3296] 4.5 4 4.2 6 4.5 4.1 5 5.6 5.1 4.2 ...
##  $ 2018                          : num [1:3296] 3.9 3.6 3.6 5.1 4 3.5 4.7 4.7 4.6 3.9 ...
##  $ 2019                          : num [1:3296] 3.2 2.9 2.9 4 3.2 2.8 3.9 3.9 3.7 3.1 ...
##  $ 2020                          : num [1:3296] 6.4 5.3 6.1 7.7 7.2 4.5 5.9 9.5 7.7 7.4 ...
##  $ 2021                          : num [1:3296] 3.4 2.8 2.9 5.5 3.4 2.4 3.9 5.1 4 3.6 ...
##  $ 2022                          : num [1:3296] 2.5 2.2 2.3 4 2.4 2.2 2.8 3.3 3 2.5 ...
##  $ 2023                          : num [1:3296] 2.5 2.2 2.3 4.4 2.5 2.1 2.4 2.9 2.8 2.4 ...
##  $ Median Household Income (2022): num [1:3296] 59703 70148 71704 41151 54309 ...
##  $ % of State Median HH Income   : num [1:3296] 1 1.175 1.201 0.689 0.91 ...

summary(unemp_county)

##      FIPS               Name                2015             2016       
##  Length:3296        Length:3296        Min.   : 1.800   Min.   : 1.600  
##  Class :character   Class :character   1st Qu.: 4.200   1st Qu.: 4.000  
##  Mode  :character   Mode  :character   Median : 5.300   Median : 4.900  
##                                        Mean   : 5.521   Mean   : 5.222  
##                                        3rd Qu.: 6.500   3rd Qu.: 6.100  
##                                        Max.   :24.600   Max.   :24.200  
##                                        NA's   :104      NA's   :104     
##       2017             2018             2019             2020       
##  Min.   : 1.500   Min.   : 1.200   Min.   : 0.800   Min.   : 1.600  
##  1st Qu.: 3.500   1st Qu.: 3.100   1st Qu.: 3.000   1st Qu.: 5.300  
##  Median : 4.300   Median : 3.900   Median : 3.700   Median : 6.600  
##  Mean   : 4.583   Mean   : 4.104   Mean   : 3.951   Mean   : 6.773  
##  3rd Qu.: 5.300   3rd Qu.: 4.800   3rd Qu.: 4.600   3rd Qu.: 8.100  
##  Max.   :19.700   Max.   :18.800   Max.   :20.700   Max.   :22.600  
##  NA's   :104      NA's   :104      NA's   :104      NA's   :103     
##       2021             2022             2023       
##  Min.   : 0.900   Min.   : 0.600   Min.   : 0.300  
##  1st Qu.: 3.500   1st Qu.: 2.700   1st Qu.: 2.800  
##  Median : 4.400   Median : 3.400   Median : 3.400  
##  Mean   : 4.651   Mean   : 3.591   Mean   : 3.586  
##  3rd Qu.: 5.500   3rd Qu.: 4.200   3rd Qu.: 4.100  
##  Max.   :19.400   Max.   :14.900   Max.   :17.300  
##  NA's   :103      NA's   :103      NA's   :103     
##  Median Household Income (2022) % of State Median HH Income
##  Min.   : 28972                 Min.   :0.4149             
##  1st Qu.: 52610                 1st Qu.:0.7675             
##  Median : 60986                 Median :0.8731             
##  Mean   : 63468                 Mean   :0.8973             
##  3rd Qu.: 70897                 3rd Qu.:1.0000             
##  Max.   :167605                 Max.   :2.3264             
##  NA's   :102                    NA's   :102

colnames(labor_demand_job)[1] <- "name"
colnames(labor_demand_size)[1] <- "name"
colnames(labor_demand_size_job)[1] <- "name"

Data Cleaning and Transformation

ind_posting <- ind_posting %>% 
  rename(Value = IHLIDXUS)

ind_posting$TransValue <- ind_posting$Value / 10

us_unemp <- us_unemp %>% 
  rename(date = observation_date,
         value = UNRATE) %>% 
  mutate(value = as.numeric(value))

county_map_join <- left_join(counties_sf, unemp_county, by = c("county_fips" = "FIPS"))

## old-style crs object detected; please recreate object with a recent sf::st_crs()

## Warning in CPL_crs_from_input(x): GDAL Message 1: CRS EPSG:2163 is deprecated.
## Its non-deprecated replacement EPSG:9311 will be used instead. To use the
## original CRS, set the OSR_USE_NON_DEPRECATED configuration option to NO.

combined_range <- range(c(unemp_county$`2019`, unemp_county$`2020`,unemp_county$`2021`), na.rm = TRUE)

labor_demand_size_long <- labor_demand_size %>% 
  pivot_longer(
    cols = -name,
    names_to = "year",
    values_to = "value"
  )

labor_demand_job_long <- labor_demand_job %>% 
  pivot_longer(
    cols = -name,
    names_to = "year",
    values_to = "value"
  )

labor_demand_size_job_long <- labor_demand_size_job %>% 
  pivot_longer(
    cols = -name,
    names_to = "size",
    values_to = "value"
  )

EDA

min(us_unemp$date)

## [1] "1948-01-01"

us_unemp_bf_1998 <- us_unemp %>%
  filter(date < as.Date("1990-01-01", format = "%Y-%m-%d"))

tick_dates_1 <- seq.Date(
  from = as.Date("1948-01-01"),
  to = as.Date("1990-01-01"),
  by = "3 year")

tick_df_1 <- data.frame(
  x = tick_dates_1,
  xend = tick_dates_1,
  y = 0,
  yend = -0.1)

us_unemp_af_1990 <- us_unemp %>%
  filter(date >= as.Date("1989-01-01", format = "%Y-%m-%d"))

tick_dates_2 <- seq.Date(
  from = as.Date("1990-01-01"),
  to = as.Date("2025-01-01"),
  by = "5 years")

tick_df_2 <- data.frame(
  x = tick_dates_2,
  xend = tick_dates_2,
  y = 0,
  yend = -0.1)

custom_years_1 <- data.frame(
  year = seq(1990, 2025, by = 5),
  date = as.Date(paste0(seq(1990, 2025, by = 5), "-01-01")),
  label = as.character(seq(1990, 2025, by = 5))
)

covid_unemp <- us_unemp %>%
  filter(date >= as.Date("2020-01-01", format = "%Y-%m-%d"))

tick_dates_3 <- seq.Date(
  from = as.Date("2020-01-01"),
  to = as.Date("2025-01-01"),
  by = "1 year")

tick_df_3 <- data.frame(
  x = tick_dates_3,
  xend = tick_dates_3,
  y = 0,
  yend = -0.1)

tick_dates_4 <- seq.Date(
  from = as.Date("1950-01-01"),
  to = as.Date("2025-01-01"),
  by = "5 year")

tick_df_4 <- data.frame(
  x = tick_dates_4,
  xend = tick_dates_4,
  y = 0,
  yend = -0.1)

points <- data.frame(x = as.Date(c("2020-01-20","2020-04-01", "2022-01-01", "2023-05-01")),
                     y = c(3.5, 14.8, 4, 3.6))

Date Visualization

Custom theme

theme_hieu_line <- function() {
  theme_classic() +
    theme(
      axis.title.x = element_blank(),
      axis.line.y.left = element_blank(),
      panel.grid.major.y = element_line(),
      axis.line.x.bottom = element_blank(),
      axis.ticks.x.bottom = element_blank(),
      plot.title = element_text(size = 20))
}

Figures

fig1 <- ggplot() + 
  geom_line(aes(x = observation_date, y = Value), linewidth = 1, color = "#5C90B2", data = ind_posting) +
  ylim(-5, NA) +
  scale_x_date(date_breaks = "1 year", date_labels = "%Y-%b") +
  theme_hieu_line() +
  theme(plot.caption = element_text(color = adjustcolor("black", alpha.f = 0.5)),
        axis.text.x.bottom = element_blank()) +
  geom_hline(yintercept = 0, color = "black") +
  annotate("rect", xmin = as.Date(min(ind_posting$observation_date), format = "%Y-%m-%d"), xmax = as.Date("2023-05-11", format = "%Y-%m-%d"), ymin = 0, ymax = max(ind_posting$Value) + 5, fill = "red", alpha = 0.08) +
  annotate("text", x = as.Date(min(ind_posting$observation_date), format = "%Y-%m-%d"), y = -5, label = "2020-03-28", size = 3.2, hjust = 0.4) +
  annotate("text", x = as.Date("2022-04-01", format = "%Y-%m-%d"),y = -5, label = "2022-04-01", size = 3.2) +
  annotate("segment", x = as.Date("2022-04-01", format = "%Y-%m-%d"), xend = as.Date("2022-04-01", format = "%Y-%m-%d"), y = 0, yend = max(ind_posting$Value), color = "black", linetype = "dashed") + 
  annotate("text", x = as.Date("2023-05-11", format = "%Y-%m-%d"), y = -5, label = "2023-05-11", size = 3.2) + 
  annotate("text", x = as.Date("2024-01-01", format = "%Y-%m-%d"), y = -5, label = "2024-01-01", size = 3.2) + 
  annotate("text", x = as.Date("2025-01-01", format = "%Y-%m-%d"), y = -5, label = "2025-01-01", size = 3.2) +
  labs(title = "Job Postings On Indeed in the United States", caption = "Units: Index, Feb, 1, 2020 = 100, Seasonally Adjusted, Frequency: Daily, 7-Day", y = "Index") +
  theme(axis.title.y.left = element_text(angle = 90))

fig1

us_unemp %>%
  ggplot() +
  geom_line(aes(x = date, y = value), color = "#5C90B2", linewidth = 0.7) +
  ylim(-1, NA) +
  theme_hieu_line() +
  geom_hline(yintercept = 0, color = "black") +
  scale_x_date(
    date_breaks = "5 year",
    date_labels = "%Y",
    limits = as.Date(c("1949-01-01", "2025-01-01"))) +
  geom_segment(data = tick_df_4, aes(x = x, xend = xend, y = y, yend = yend), color = "black") +
  theme(axis.text.x.bottom = element_text(vjust = 18)) +
  annotate("segment", x = as.Date("1995-01-01"), xend = as.Date("1995-01-01"), y = 1, yend = 14, linetype = "dashed", linewidth = 0.5, color = "red") +
  annotate("rect", xmin = as.Date("2020-01-19", format = "%Y-%m-%d"), xmax = as.Date("2023-05-11", format = "%Y-%m-%d"), ymin = 0, ymax = 15, fill = "red", alpha = 0.08) +
  annotate("rect", xmin = as.Date("1990-01-01", format = "%Y-%m-%d"), xmax = as.Date("1992-08-01", format = "%Y-%m-%d"), ymin = 0, ymax = 15, fill = "grey", alpha = 0.15) +
  annotate("rect", xmin = as.Date("2000-06-01", format = "%Y-%m-%d"), xmax = as.Date("2003-08-01", format = "%Y-%m-%d"), ymin = 0, ymax = 15, fill = "grey", alpha = 0.15) +
  annotate("rect", xmin = as.Date("2007-01-01", format = "%Y-%m-%d"), xmax = as.Date("2010-06-01", format = "%Y-%m-%d"), ymin = 0, ymax = 15, fill = "grey", alpha = 0.15) +
  annotate("rect", xmin = as.Date("1953-01-01", format = "%Y-%m-%d"), xmax = as.Date("1954-10-01", format = "%Y-%m-%d"), ymin = 0, ymax = 15, fill = "grey", alpha = 0.15) +
  annotate("rect", xmin = as.Date("1957-01-01", format = "%Y-%m-%d"), xmax = as.Date("1958-06-01", format = "%Y-%m-%d"), ymin = 0, ymax = 15, fill = "grey", alpha = 0.15) +
  annotate("rect", xmin = as.Date("1960-04-01", format = "%Y-%m-%d"), xmax = as.Date("1961-08-01", format = "%Y-%m-%d"), ymin = 0, ymax = 15, fill = "grey", alpha = 0.15) +
  annotate("rect", xmin = as.Date("2007-01-01", format = "%Y-%m-%d"), xmax = as.Date("2010-06-01", format = "%Y-%m-%d"), ymin = 0, ymax = 15, fill = "grey", alpha = 0.15) +
  annotate("rect", xmin = as.Date("1970-01-01", format = "%Y-%m-%d"), xmax = as.Date("1971-06-01", format = "%Y-%m-%d"), ymin = 0, ymax = 15, fill = "grey", alpha = 0.15) +
  annotate("rect", xmin = as.Date("1974-01-01", format = "%Y-%m-%d"), xmax = as.Date("1975-06-01", format = "%Y-%m-%d"), ymin = 0, ymax = 15, fill = "grey", alpha = 0.15) +
  annotate("rect", xmin = as.Date("1979-06-01", format = "%Y-%m-%d"), xmax = as.Date("1983-06-01", format = "%Y-%m-%d"), ymin = 0, ymax = 15, fill = "grey", alpha = 0.15) +
  annotate("text", x = as.Date("1995-01-01"),y = 14.5, label = "Birth of World Wide Web", color = "red") +
  labs(y = "Percentage", title = "Recorded History Trend of Unemployment Rate")

# Before the internet boom of 1990 (dot com bubble)
fig2 <- ggplot() +
  geom_line(aes(x = date, y = value), color = "#5C90B2", linewidth = 0.8, data = us_unemp_bf_1998) +
  ylim(-0.1,15) +
  theme_hieu_line() +
  theme(axis.text.x.bottom = element_text(vjust = 10)) +
  geom_hline(yintercept = 0, color = "black") +
  scale_x_date(date_breaks = "3 year", date_labels = "%Y") +
  geom_segment(data = tick_df_1, aes(x = x, xend = xend, y = y, yend = yend), color = "black") +
  labs(y = "Percentage")

# After 1995 dot com bubble
fig3 <- ggplot() +
  geom_line(aes(x = date, y = value), color = "#5C90B2", linewidth = 0.8, data = us_unemp_af_1990) +
  ylim(-1,15.5) +
  theme_hieu_line() +
  geom_hline(yintercept = 0, color = "black") +
  scale_x_date(date_breaks = "5 years", date_labels = "%Y") +
  geom_segment(data = tick_df_2, aes(x = x, xend = xend, y = y, yend = yend), color = "black") +
  labs(y = "Percentage", title = "Since the Globalization of the World Wide Web")  +
  theme(axis.text.x.bottom = element_text(vjust = 10)) +
  annotate("rect", xmin = as.Date("2020-01-19", format = "%Y-%m-%d"), xmax = as.Date("2023-05-11", format = "%Y-%m-%d"), ymin = 0, ymax = 15, fill = "red", alpha = 0.08) +
  theme(axis.text.x.bottom = element_blank()) +
  geom_text(data = custom_years_1,aes(x = date, y = -1, label = label),
            vjust = -1,
            size = 3) +
  annotate("rect", xmin = as.Date("1990-01-01", format = "%Y-%m-%d"), xmax = as.Date("1992-08-01", format = "%Y-%m-%d"), ymin = 0, ymax = 15, fill = "grey", alpha = 0.3) +
  annotate("rect", xmin = as.Date("2000-06-01", format = "%Y-%m-%d"), xmax = as.Date("2003-08-01", format = "%Y-%m-%d"), ymin = 0, ymax = 15, fill = "grey", alpha = 0.3) +
  annotate("rect", xmin = as.Date("2007-01-01", format = "%Y-%m-%d"), xmax = as.Date("2010-06-01", format = "%Y-%m-%d"), ymin = 0, ymax = 15, fill = "grey", alpha = 0.3) +
  annotate("text", x = as.Date("1991-04-01"), y = 15.4, label = "1990 Recession", size = 3) +
  annotate("text", x = as.Date("2002-03-01"), y = 15.4, label = "'.com' Bubble Burst", size = 3) +
  annotate("text", x = as.Date("2008-06-01"), y = 15.4, label = "Great Recession", size = 3) +
  annotate("text", x = as.Date("2021-10-01"), y = 15.4, label = "COVID 19", size = 3, color = "red", alpha = 0.8)
  
fig3

fig4 <- ggplot() +
  geom_line(aes(x = date, y = value), color = "#5C90B2", linewidth = 0.8, data = covid_unemp) +
  ylim(-0.1,16) +
  theme_hieu_line() +
  geom_hline(yintercept = 0, color = "black") +
  scale_x_date(date_breaks = "1 year", date_labels = "%Y") +
  geom_segment(data = tick_df_3, aes(x = x, xend = xend, y = y, yend = yend), color = "black") +
  theme(axis.text.x.bottom = element_text(vjust = 10)) + 
  labs(y = "Percentage") +
  annotate("text", x = as.Date("2020-08-20"), y = 3, label = "First Case in U.S.", size = 3.5, color = "red") +
  geom_point(data = points, aes(x = x, y = y), color = "red", size = 2) +
  annotate("text", x = as.Date("2021-05-01"), y = 15.2, label = "Peak Unemployment (14.8%)", size = 3.5, color = "red") +
  annotate("text", x = as.Date("2022-07-01"), y = 4.8, label = "Peak COVID cases", size = 3.5, color = "red") +
  annotate("text", x = as.Date("2024-02-01"), y = 2.7, label = "Pandemic Officially End", size = 3.5, color = "red")

fig4

points

##            x    y
## 1 2020-01-20  3.5
## 2 2020-04-01 14.8
## 3 2022-01-01  4.0
## 4 2023-05-01  3.6

ggplot() +
  geom_line(aes(x = observation_date, y = TransValue), 
            data = ind_posting, color = "#5C90B2", linewidth = 1) +
  geom_line(aes(x = date, y = value), 
            data = covid_unemp, color = "#E15759", linewidth = 0.8) +
  scale_y_continuous(
  name = "Unemployment Rate (%)",
  sec.axis = sec_axis(
    trans = ~ ., 
    name = "Job Demand Index (Indeed)",
    labels = function(x) x * 10  )) +
  scale_x_date(date_breaks = "1 year", date_labels = "%Y", limits = as.Date(c("2019-10-01", "2025-01-01"))) +
  theme_hieu_line() +
  geom_hline(yintercept = 0, color = "black") +
  theme(
    axis.text.x.bottom = element_text(vjust = 10),
    axis.title.y = element_text(color = "#E15759"),       
    axis.title.y.right = element_text(color = "#5C90B2")) +
  geom_segment(data = tick_df_3, aes(x = x, xend = xend, y = y, yend = yend), color = "black") +
  annotate("segment", 
           x = as.Date("2020-01-01"), 
           xend = min(ind_posting$observation_date), 
           y = 10, yend = 8.393, 
           linetype = "dashed", linewidth = 1, color = "#5C90B2") +
  theme(axis.line.y.right = element_blank()) +
  annotate("segment", x = as.Date("2020-01-20"), xend = as.Date("2020-01-20"), y = 0, yend = 9.7, linetype = "dashed", linewidth = 0.7, color = "grey") +
  annotate("segment", x = as.Date("2020-04-01"), xend = as.Date("2020-04-01"), y = 0, yend = 14.7, linetype = "dashed", linewidth = 0.7, color = "grey") +
  annotate("segment", x = as.Date("2022-01-01"), xend = as.Date("2022-01-01"), y = 0, yend = 15.3, linetype = "dashed", linewidth = 0.7, color = "grey") +
  annotate("segment", x = as.Date("2023-05-01"), xend = as.Date("2023-05-01"), y = 0, yend = 13.6, linetype = "dashed", linewidth = 0.7, color = "grey") +
  annotate("text", x = as.Date("2019-10-01"), y = 3, label = "1st COVID", size = 3) +
  annotate("text", x = as.Date("2019-10-01"), y = 2.5, label = "case in", size = 3) +
  annotate("text", x = as.Date("2019-10-01"), y = 2, label = "the U.S.", size = 3) +
  annotate("text", x = as.Date("2020-09-01"), y = 15.9, label = "Peak Unemployment", size = 3) +
  annotate("text", x = as.Date("2020-09-01"), y = 15.3, label = "Rate (14.8%)", size = 3) +
  annotate("text", x = as.Date("2022-06-01"), y = 14, label = "Peak COVID", size = 3) +
  annotate("text", x = as.Date("2022-06-01"), y = 13.4, label = "(~62M Cases)", size = 3) +
  annotate("text", x = as.Date("2023-09-20"), y = 11, label = "Biden Declare", size = 3) +
  annotate("text", x = as.Date("2023-12-20"), y = 10.4, label = "Pandemic Officially Over", size = 3)

points

##            x    y
## 1 2020-01-20  3.5
## 2 2020-04-01 14.8
## 3 2022-01-01  4.0
## 4 2023-05-01  3.6

fig5 <- ggplot() +
  geom_sf(data = county_map_join, aes(fill = `2019`), linewidth = 0.1) +
  coord_sf(crs=st_crs(4326)) +
  theme_map() +
  theme(legend.position = c(0.2,-0.15),
        legend.title = element_blank(),
        plot.margin = margin(1,1,50,1)) +
  scale_fill_gradientn(
    colors = c("lightblue","#FFFF99", "orange", "darkred"),  
    na.value = "lightblue",
    guide = guide_colorbar(barheight = 0.8, barwidth = 20, direction = "horizontal"),
    limits = combined_range, 
    values = scales::rescale(c(0, 0.3, 0.5, 1)),
    breaks = c(5, 10, 15, 20),
    labels = c("5%", "10%", "15%", "20%")) +
  geom_sf(data = states_sf, color = "black", fill = NA, linewidth = 0.15) 

## Warning: A numeric `legend.position` argument in `theme()` was deprecated in ggplot2
## 3.5.0.
## ℹ Please use the `legend.position.inside` argument of `theme()` instead.
## This warning is displayed once every 8 hours.
## Call `lifecycle::last_lifecycle_warnings()` to see where this warning was
## generated.

## Coordinate system already present. Adding new coordinate system, which will
## replace the existing one.

fig5

## old-style crs object detected; please recreate object with a recent sf::st_crs()

fig6 <- ggplot() +
  geom_sf(data = county_map_join, aes(fill = `2020`), linewidth = 0.1) +
  coord_sf(crs=st_crs(4326)) +
  theme_map() +
  theme(legend.position = c(0.2,-0.15),
        legend.title = element_blank(),
        plot.margin = margin(1,1,50,1)) +
  scale_fill_gradientn(
    colors = c("lightblue","#FFFF99", "orange", "darkred"),  
    na.value = "lightblue",
    guide = guide_colorbar(barheight = 0.8, barwidth = 20, direction = "horizontal"),
    limits = combined_range, 
    values = scales::rescale(c(0, 0.3, 0.5, 1)),
    breaks = c(5, 10, 15, 20),
    labels = c("5%", "10%", "15%", "20%")) +
  geom_sf(data = states_sf, color = "black", fill = NA, linewidth = 0.2) 

## Coordinate system already present. Adding new coordinate system, which will
## replace the existing one.

fig6

## old-style crs object detected; please recreate object with a recent sf::st_crs()

fig7 <- ggplot() +
  geom_sf(data = county_map_join, aes(fill = `2021`), linewidth = 0.1) +
  coord_sf(crs=st_crs(4326)) +
  theme_map() +
  theme(legend.position = c(0.2,-0.15),
        legend.title = element_blank(),
        plot.margin = margin(1,1,50,1)) +
  scale_fill_gradientn(
    colors = c("lightblue","#FFFF99", "orange", "darkred"),  
    na.value = "lightblue",
    guide = guide_colorbar(barheight = 0.8, barwidth = 20, direction = "horizontal"),
    limits = combined_range,
    values = scales::rescale(c(0, 0.3, 0.5, 1)),
    breaks = c(5, 10, 15, 20),
    labels = c("5%", "10%", "15%", "20%")) +
  geom_sf(data = states_sf, color = "black", fill = NA, linewidth = 0.2) 

## Coordinate system already present. Adding new coordinate system, which will
## replace the existing one.

fig7

## old-style crs object detected; please recreate object with a recent sf::st_crs()

labor_demand_size

## # A tibble: 4 × 4
##   name                           `2023_2024` `2021_2022` `2017_2019`
##   <chr>                                <dbl>       <dbl>       <dbl>
## 1 Small Metros and Micropolitans       0.160       0.125       0.136
## 2 Medium Metros                        0.222       0.200       0.177
## 3 Large Fringe Metros                  0.238       0.242       0.228
## 4 Large Central Metros                 0.381       0.434       0.459

ggplot() +
  geom_bar(aes(x = name, y = value, fill = year), position = "dodge", stat = "identity", data = labor_demand_size_long) +
  theme_classic() +
  scale_fill_viridis_d(option = "E",
                       labels = c("2017_2019" = "Pre COVID", "2021_2022" = "COVID", "2023_2024" = "Post COVID")) +
  theme(axis.line = element_blank(),
        axis.ticks = element_blank(), 
        plot.title = element_text(size = 20),
        legend.title = element_blank(),
        legend.position = "bottom",
        axis.title.x.bottom = element_blank()) +
  labs(y = "Percentage", title = "Job Listing Proportion By Location Type") 

ggplot() +
  geom_bar(aes(x = name, y = value, fill = year), position = "dodge", stat = "identity", data = labor_demand_job_long) +
  theme_classic() +
  scale_fill_viridis_d(option = "E",
                       labels = c("2017-2019" = "Pre COVID", "2021-2022" = "COVID", "2023-2024" = "Post COVID")) +
  theme(axis.line = element_blank(),
        axis.ticks = element_blank(), 
        plot.title = element_text(size = 20),
        legend.title = element_blank(),
        legend.position = "bottom",
        axis.title.x.bottom = element_blank()) +
  labs(y = "Percentage", title = "Job Listing Proportion By Location Type") +
  scale_x_discrete(labels = function(x) gsub(" ", "\n", x))

ggplot() +
  geom_bar(aes(x = name,y = value,fill = factor(year, levels = c("2023-2024", "2021-2022", "2017-2019"))),
    position = "dodge",
    stat = "identity",
    data = labor_demand_job_long) +
  theme_classic() +
  scale_fill_viridis_d(
    option = "E",
    direction = -1,
    labels = c(
      "2017-2019" = "Pre COVID",
      "2021-2022" = "COVID",
      "2023-2024" = "Post COVID"),
    guide = guide_legend(reverse = TRUE)) +
  theme(
    axis.line = element_blank(),
    axis.ticks = element_blank(),
    plot.title = element_text(size = 20),
    legend.title = element_blank(),
    legend.position = "right",
    axis.title.x.bottom = element_blank(),
    axis.title.y.left = element_blank()) +
  coord_flip()

ggplot() +
  geom_tile(aes(x = factor(name, levels = c("Computer and Mathematical Occupations", 
                                            "Business and Financial Operations Occupations", 
                                            "Office and Administrative Support Occupations", 
                                            "Sales and Related Occupations", 
                                            "Food Preparation and Serving Related Occupations", 
                                            "Healthcare Practitioners and Technical Occupations")),
                y = factor(size, levels = c(
                  "Small Metros and Micropolitan Areas", 
                  "Medium Metro", 
                  "Large Fringe Metro", 
                  "Large Central Metro")), fill = value), data = labor_demand_size_job_long) + 
  scale_x_discrete(labels = function(x) gsub(" ", "\n", x)) +
  scale_y_discrete(labels = function(x) gsub(" ", "\n", x)) +
  scale_fill_viridis_c(option = "H")+
  theme_minimal() +
  theme(legend.title = element_blank(),
        axis.title = element_blank(),
        axis.ticks = element_blank(),
        plot.title = element_text(size = 18)) +
  guides(fill=guide_colorbar(ticks.colour = NA, barwidth = 1, barheight = 15)) +
  labs(title = "Shift in Occupation Demand by Location Type")